Is this post about Machine Learning? Well, not really, but it is highly related. In this post I will explain how to use a web browser to get information about the environment (pictures and sound). Then, I will present a simple way to process and interact with this information. Why do I do that? At first, simply because I am (trying) to play with tensorflow, chatbots etc, and I need a simple way to grab information to create a training set... But with the evolution of my code, I am now using it alongside with the cloud API of AWS. Welcome to my world.